sh0ck0r
/

deepseek-coder-v2-lite-FP8-Dynamic

Text Generation

compressed-tensors

text-generation-inference

Model card Files Files and versions

deepseek-coder-v2-lite-FP8-Dynamic / recipe.yaml

sh0ck0r's picture

Upload FP8 quantized version of deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct

88381da verified 4 months ago

history blame contribute delete

136 Bytes

	default_stage:
	default_modifiers:
	QuantizationModifier:
	targets: [Linear]
	ignore: [lm_head]
	scheme: FP8_DYNAMIC